| { | |
| "best_metric": 1.3218564987182617, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.18392495861688432, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003678499172337686, | |
| "eval_loss": 2.6280200481414795, | |
| "eval_runtime": 65.4834, | |
| "eval_samples_per_second": 17.485, | |
| "eval_steps_per_second": 4.383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036784991723376862, | |
| "grad_norm": 1.1980564594268799, | |
| "learning_rate": 4.0400000000000006e-05, | |
| "loss": 2.5135, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0073569983446753725, | |
| "grad_norm": 1.2913352251052856, | |
| "learning_rate": 8.080000000000001e-05, | |
| "loss": 1.9668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011035497517013059, | |
| "grad_norm": 1.0023733377456665, | |
| "learning_rate": 0.00012119999999999999, | |
| "loss": 1.6289, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014713996689350745, | |
| "grad_norm": 1.1973117589950562, | |
| "learning_rate": 0.00016160000000000002, | |
| "loss": 1.5254, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01839249586168843, | |
| "grad_norm": 1.1962615251541138, | |
| "learning_rate": 0.000202, | |
| "loss": 1.3739, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01839249586168843, | |
| "eval_loss": 1.5840084552764893, | |
| "eval_runtime": 65.6655, | |
| "eval_samples_per_second": 17.437, | |
| "eval_steps_per_second": 4.371, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022070995034026118, | |
| "grad_norm": 0.9154727458953857, | |
| "learning_rate": 0.00020175396907624226, | |
| "loss": 1.6272, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025749494206363802, | |
| "grad_norm": 0.8820514678955078, | |
| "learning_rate": 0.0002010170749428986, | |
| "loss": 1.5373, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02942799337870149, | |
| "grad_norm": 0.9362473487854004, | |
| "learning_rate": 0.00019979290767411438, | |
| "loss": 1.4742, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.033106492551039174, | |
| "grad_norm": 0.9134910702705383, | |
| "learning_rate": 0.0001980874312897702, | |
| "loss": 1.428, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03678499172337686, | |
| "grad_norm": 1.1899622678756714, | |
| "learning_rate": 0.00019590895469937675, | |
| "loss": 1.3833, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03678499172337686, | |
| "eval_loss": 1.4966574907302856, | |
| "eval_runtime": 65.9742, | |
| "eval_samples_per_second": 17.355, | |
| "eval_steps_per_second": 4.35, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04046349089571455, | |
| "grad_norm": 0.8478430509567261, | |
| "learning_rate": 0.0001932680912219027, | |
| "loss": 1.5648, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.044141990068052236, | |
| "grad_norm": 0.9589736461639404, | |
| "learning_rate": 0.00019017770687875164, | |
| "loss": 1.4468, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.047820489240389924, | |
| "grad_norm": 0.9376389384269714, | |
| "learning_rate": 0.000186652857711799, | |
| "loss": 1.4539, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.051498988412727605, | |
| "grad_norm": 0.8931785821914673, | |
| "learning_rate": 0.00018271071643186968, | |
| "loss": 1.3959, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05517748758506529, | |
| "grad_norm": 1.1111578941345215, | |
| "learning_rate": 0.00017837048875501678, | |
| "loss": 1.3041, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05517748758506529, | |
| "eval_loss": 1.4765535593032837, | |
| "eval_runtime": 66.144, | |
| "eval_samples_per_second": 17.311, | |
| "eval_steps_per_second": 4.339, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05885598675740298, | |
| "grad_norm": 0.8667774796485901, | |
| "learning_rate": 0.00017365331983420376, | |
| "loss": 1.5348, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06253448592974066, | |
| "grad_norm": 0.8413021564483643, | |
| "learning_rate": 0.0001685821912422447, | |
| "loss": 1.5303, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06621298510207835, | |
| "grad_norm": 0.8751350045204163, | |
| "learning_rate": 0.00016318180900789148, | |
| "loss": 1.3763, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06989148427441604, | |
| "grad_norm": 0.9402979016304016, | |
| "learning_rate": 0.00015747848325054544, | |
| "loss": 1.3309, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07356998344675372, | |
| "grad_norm": 1.0289543867111206, | |
| "learning_rate": 0.0001515, | |
| "loss": 1.2805, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07356998344675372, | |
| "eval_loss": 1.4655332565307617, | |
| "eval_runtime": 67.0945, | |
| "eval_samples_per_second": 17.065, | |
| "eval_steps_per_second": 4.278, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07724848261909141, | |
| "grad_norm": 0.7757532000541687, | |
| "learning_rate": 0.00014527548582569683, | |
| "loss": 1.4872, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0809269817914291, | |
| "grad_norm": 0.8359755873680115, | |
| "learning_rate": 0.00013883526593500714, | |
| "loss": 1.4299, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08460548096376679, | |
| "grad_norm": 0.8961185812950134, | |
| "learning_rate": 0.0001322107164318697, | |
| "loss": 1.404, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08828398013610447, | |
| "grad_norm": 0.9134626984596252, | |
| "learning_rate": 0.00012543411145556643, | |
| "loss": 1.3383, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09196247930844216, | |
| "grad_norm": 1.0392701625823975, | |
| "learning_rate": 0.00011853846594435998, | |
| "loss": 1.2476, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09196247930844216, | |
| "eval_loss": 1.4170724153518677, | |
| "eval_runtime": 65.8266, | |
| "eval_samples_per_second": 17.394, | |
| "eval_steps_per_second": 4.36, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09564097848077985, | |
| "grad_norm": 0.7596132755279541, | |
| "learning_rate": 0.00011155737479003301, | |
| "loss": 1.5365, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09931947765311752, | |
| "grad_norm": 0.8383329510688782, | |
| "learning_rate": 0.00010452484916695262, | |
| "loss": 1.4248, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10299797682545521, | |
| "grad_norm": 0.8279966711997986, | |
| "learning_rate": 9.747515083304742e-05, | |
| "loss": 1.3758, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1066764759977929, | |
| "grad_norm": 0.9013005495071411, | |
| "learning_rate": 9.044262520996702e-05, | |
| "loss": 1.3529, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.11035497517013058, | |
| "grad_norm": 1.153868317604065, | |
| "learning_rate": 8.346153405564004e-05, | |
| "loss": 1.2002, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11035497517013058, | |
| "eval_loss": 1.3866181373596191, | |
| "eval_runtime": 65.7201, | |
| "eval_samples_per_second": 17.422, | |
| "eval_steps_per_second": 4.367, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11403347434246827, | |
| "grad_norm": 0.7157303690910339, | |
| "learning_rate": 7.656588854443357e-05, | |
| "loss": 1.4783, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11771197351480596, | |
| "grad_norm": 0.7488118410110474, | |
| "learning_rate": 6.978928356813031e-05, | |
| "loss": 1.4637, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.12139047268714365, | |
| "grad_norm": 0.7784683108329773, | |
| "learning_rate": 6.316473406499288e-05, | |
| "loss": 1.3839, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12506897185948132, | |
| "grad_norm": 0.7745943665504456, | |
| "learning_rate": 5.672451417430317e-05, | |
| "loss": 1.2398, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.12874747103181902, | |
| "grad_norm": 1.1556774377822876, | |
| "learning_rate": 5.050000000000002e-05, | |
| "loss": 1.24, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.12874747103181902, | |
| "eval_loss": 1.3593629598617554, | |
| "eval_runtime": 65.7086, | |
| "eval_samples_per_second": 17.425, | |
| "eval_steps_per_second": 4.368, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1324259702041567, | |
| "grad_norm": 0.7711465358734131, | |
| "learning_rate": 4.452151674945458e-05, | |
| "loss": 1.4537, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1361044693764944, | |
| "grad_norm": 0.7745826840400696, | |
| "learning_rate": 3.8818190992108515e-05, | |
| "loss": 1.4033, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13978296854883207, | |
| "grad_norm": 0.7452824115753174, | |
| "learning_rate": 3.3417808757755355e-05, | |
| "loss": 1.2894, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.14346146772116977, | |
| "grad_norm": 0.8825933933258057, | |
| "learning_rate": 2.8346680165796253e-05, | |
| "loss": 1.3367, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14713996689350745, | |
| "grad_norm": 0.9986250996589661, | |
| "learning_rate": 2.362951124498323e-05, | |
| "loss": 1.2489, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14713996689350745, | |
| "eval_loss": 1.3324865102767944, | |
| "eval_runtime": 65.63, | |
| "eval_samples_per_second": 17.446, | |
| "eval_steps_per_second": 4.373, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15081846606584515, | |
| "grad_norm": 0.7403445839881897, | |
| "learning_rate": 1.928928356813032e-05, | |
| "loss": 1.4268, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.15449696523818282, | |
| "grad_norm": 0.7790653109550476, | |
| "learning_rate": 1.5347142288200977e-05, | |
| "loss": 1.3724, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.1581754644105205, | |
| "grad_norm": 0.8011258840560913, | |
| "learning_rate": 1.1822293121248375e-05, | |
| "loss": 1.3301, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.1618539635828582, | |
| "grad_norm": 0.8102395534515381, | |
| "learning_rate": 8.731908778097302e-06, | |
| "loss": 1.2836, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.16553246275519587, | |
| "grad_norm": 0.930636465549469, | |
| "learning_rate": 6.09104530062326e-06, | |
| "loss": 1.2365, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.16553246275519587, | |
| "eval_loss": 1.3237847089767456, | |
| "eval_runtime": 65.7933, | |
| "eval_samples_per_second": 17.403, | |
| "eval_steps_per_second": 4.362, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.16921096192753357, | |
| "grad_norm": 0.7757034301757812, | |
| "learning_rate": 3.912568710229791e-06, | |
| "loss": 1.4375, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.17288946109987124, | |
| "grad_norm": 0.7832618951797485, | |
| "learning_rate": 2.2070923258856255e-06, | |
| "loss": 1.339, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.17656796027220895, | |
| "grad_norm": 0.7737963795661926, | |
| "learning_rate": 9.829250571013935e-07, | |
| "loss": 1.3189, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.18024645944454662, | |
| "grad_norm": 0.8774094581604004, | |
| "learning_rate": 2.4603092375775605e-07, | |
| "loss": 1.267, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.18392495861688432, | |
| "grad_norm": 1.0865882635116577, | |
| "learning_rate": 0.0, | |
| "loss": 1.2489, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18392495861688432, | |
| "eval_loss": 1.3218564987182617, | |
| "eval_runtime": 65.6585, | |
| "eval_samples_per_second": 17.439, | |
| "eval_steps_per_second": 4.371, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.886804283392e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |